# Generative/Agentic AI Architect* Home* Generative/Agentic AI Architect* November 16, 2026* 0 Comments* By Roberte OkoyaContext: Seniority 9 years and over. Reporting to the Architecture and Private Cloud team, responsible for supporting projects around containerized applications in terms of architecture, design, and CI/CD, for the various business lines of the Group and for the benefit of both internal employees and clients. The AI Architect is responsible for the design and consistency of the architectures of the Group's generative and agentic AI solutions. They support their industrialization on the private and public cloud, guide technological choices (models, frameworks, platforms), ensure security, compliance, and cost control, and disseminate best practices within the teams.MISSIONS: • AI Solution Architecture: Design target architectures for generative and agentic AI use cases (assistants, RAGs, autonomous agents, multi-agent systems); define reference patterns and reusable components. • Monitoring and Community: Conduct continuous technological monitoring of the AI ecosystem; proactively propose market solutions; contribute to the management of the Group's agentic AI community. • AI Platform: Contribute to the design and evolution of the Group's AI platform (LLM serving, model gateway, vector databases, agent orchestration) on OpenShift and the trusted public cloud. • Security, Compliance, and Governance: Integrate security requirements (prompt injection, data leaks, agent access management), regulatory requirements (AI Act, DORA, GDPR), and responsible AI principles; participate in security validation committees. • Quality and performance: define model and agent evaluation strategies (relevance, hallucinations, latency); implement LLMOps observability and FinOps monitoring of model consumption. • Documentation and collaboration: write architecture documentation and technical specifications; work closely with IT and business teams; participate in architecture reviews. • Industrialization: technically manage the transition of POCs and pilots to production, in conjunction with the infrastructure, security, and production teams; ensure the stability, operation, and evolution of deployed solutions. In particular, this position contributes to the implementation of the Group's agentic AI plan and facilitates the integration of AI into the development pipeline. As such, the responsibilities include: • Designing and prototyping agentic agents and workflows, and participating in the definition of the modular architecture of the AI platform. • Implement secure and governed exposure of IT system tools and data to agents via the Model Context Protocol (MCP) and Group APIs. • Industrialize the deployment of models and agents using a GitOps approach (ArgoCD, OpenShift GitOps) and automate LLMOps pipelines (evaluation, versioning of prompts, monitoring). • Serve as the team's AI expert; mentor and support developers in adopting AI and code assistants. • Provide project support and guidance.Specific Expertise: • At least 9 years of experience in software development and architecture, including at least 3 years on AI or generative AI projects. Excellent command of Python (FastAPI) and good knowledge of Java (Quarkus, LangChain4j). o Generative and Agentic AI: proficiency in LLM (GPT, Claude, Gemini, Mistral, Llama), prompt engineering, RAG architectures, and agentic frameworks (LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, Google ADK). Knowledge of MCP and A2A protocols. o AI Platforms: experience with Vertex AI, Azure OpenAI, and/or Amazon Bedrock. Experience serving open-source models on private clouds (OpenShift AI, vLLM, KServe, Ollama) and model gateways (LiteLLM). Knowledge of GPU constraints. • Vector data and databases: Knowledge of pgvector, Milvus, Qdrant, and OpenSearch/Elasticsearch. Proficiency in chunking, embeddings, hybrid search, and reranking. Strong command of SQL and relational databases, particularly PostgreSQL. • LLMOps and quality: Experience with model and agent evaluation (Ragas, DeepEval), observability and traceability (Langfuse, OpenTelemetry, MLflow), guardrails, prompt management, and cost tracking (FinOps). • Containers and DevOps: Excellent command of Docker, Kubernetes, and OpenShift. Experience with CI/CD pipelines (Git, Jira, Jenkins) and GitOps approaches with ArgoCD. Advanced use of AI code assistants (Claude Code, GitHub Copilot). o Architecture, security and governance: knowledge of private cloud infrastructure components (network, storage, reverse proxy, TLS certificates), AI application security (OWASP Top 10 for LLM, secrets management, RBAC), the AI Act and the challenges of responsible AI.Application: CV + cover letter + copies of diplomas to be sent to contact@keoni.frFounded in 2008, Kéoni Consulting is an IT consulting and engineering firm specializing in the banking, financial markets, insurance, and industrial sectors. We are the partner for major accounts in their digital transformation. We help them transform their business model, align their operational processes, select the best technologies, and mitigate and overcome the risks associated with digitalization. Kéoni Consulting helps companies to: • Make a difference • Innovate and create • Reinvent their business • Satisfy customers • Gain a competitive advantage • Become the leader in their sector • Become the leader in your sector • Our activity covers the entire information systems lifecycle (Project Management, Business Analysis Consulting, Design, Implementation, Maintenance, Production, and Operations).**Job Category:** Digital Transformation**Job Type:** Full Time**Work location:** Europe